A Compact Deep Learning Model for Robust Facial Expression Recognition

Chieh-Ming Kuo, Shang-Hong Lai, Michel Sarkis

CVPRW 2018 pp. 2121-2129

doi:10.1109/CVPRW.2018.00286 /cvprw/2018/kuo2018cvprw-compact/

Abstract

In this paper, we propose a compact frame-based facial expression recognition framework for facial expression recognition which achieves very competitive performance with respect to state-of-the-art methods while using much less parameters. The proposed framework is extended to a frame-to-sequence approach by exploiting temporal information with gated recurrent units. In addition, we develop an illumination augmentation scheme to alleviate the overfitting problem when training the deep networks with hybrid data sources. Finally, we demonstrate the performance improvement by using the proposed technique on some public datasets.

PDF CVPRW Semantic Scholar

Cite

Text

Kuo et al. "A Compact Deep Learning Model for Robust Facial Expression Recognition." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018. doi:10.1109/CVPRW.2018.00286

Markdown

[Kuo et al. "A Compact Deep Learning Model for Robust Facial Expression Recognition." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018.](https://mlanthology.org/cvprw/2018/kuo2018cvprw-compact/) doi:10.1109/CVPRW.2018.00286

BibTeX

@inproceedings{kuo2018cvprw-compact,
  title     = {{A Compact Deep Learning Model for Robust Facial Expression Recognition}},
  author    = {Kuo, Chieh-Ming and Lai, Shang-Hong and Sarkis, Michel},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2018},
  pages     = {2121-2129},
  doi       = {10.1109/CVPRW.2018.00286},
  url       = {https://mlanthology.org/cvprw/2018/kuo2018cvprw-compact/}
}